INDEX

Explanations

concepts related to significant changes or impacts in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 affair

-0.16

 standpoint

-0.16

oretical

-0.15

Ä±rak

-0.15

gÄ±

-0.14

 situation

-0.14

 Reputation

-0.14

icast

-0.14

NullException

-0.13

è«¸

-0.13

POSITIVE LOGITS

 amounts

0.40

 levels

0.34

levels

0.26

 quantities

0.24

 sums

0.24

amount

0.22

ily

0.21

Levels

0.21

 degrees

0.20

 Levels

0.20

Activations Density 0.383%

concepts related to significant changes or impacts in various contexts

No Comments

No Known Activations